Update README.md
Browse files
README.md
CHANGED
|
@@ -6,9 +6,10 @@ license: apache-2.0
|
|
| 6 |
---
|
| 7 |
|
| 8 |
# Wav2vec2-base for Danish
|
| 9 |
-
|
| 10 |
This wav2vec2-base model has been pretrained on ~1300 hours of danish speech data. The pretraining data consists of podcasts and audiobooks and is unfortunately not public available. However, we were allowed to distribute the pretrained model.
|
| 11 |
|
|
|
|
|
|
|
| 12 |
The pre-training was done using the fairseq library in January 2021.
|
| 13 |
|
| 14 |
It needs to be fine-tuned to perform speech recognition.
|
|
|
|
| 6 |
---
|
| 7 |
|
| 8 |
# Wav2vec2-base for Danish
|
|
|
|
| 9 |
This wav2vec2-base model has been pretrained on ~1300 hours of danish speech data. The pretraining data consists of podcasts and audiobooks and is unfortunately not public available. However, we were allowed to distribute the pretrained model.
|
| 10 |
|
| 11 |
+
This model was pretrained on 16kHz sampled speech audio. When using the model, make sure to use speech audio sampled at 16kHz.
|
| 12 |
+
|
| 13 |
The pre-training was done using the fairseq library in January 2021.
|
| 14 |
|
| 15 |
It needs to be fine-tuned to perform speech recognition.
|